GLM-4.7
Last verified August 3, 2026 · Zhipu pricing ↗$0.600/1M input · $2.20/1M output · 200K context · Zhipu
GLM-4.7 costs $0.600 per 1M input tokens and $2.20 per 1M output tokens from Zhipu, with a 200K-token context window. A typical chat reply (1,500 tokens in, 400 out) costs $0.0018, or $17.80 per 10,000 requests. On that workload it is cheaper than 102 of the 168 other buyable models tracked here.
Count Tokens
—
Tokens
—
Input Cost
—
Output Cost
Estimate Monthly Cost
Monthly Cost Estimator
Quick:
<$0.0001/mo
Pick a preset above or enter custom usage
What GLM-4.7 Costs Per Request
At $0.600 per 1M input and $2.20 per 1M output tokens, before caching or batch discounts.
| Workload | Input / output tokens | Per request | Per 10,000 requests |
|---|---|---|---|
| Chat reply | 1,500 / 400 | $0.0018 | $17.80 |
| RAG answer over retrieved docs | 8,000 / 600 | $0.0061 | $61.20 |
| Coding-agent step | 30,000 / 2,000 | $0.022 | $224.00 |
GLM-4.7 vs Similarly Priced Models
Nearest buyable models by price, with the RAG answer above (8,000 in / 600 out) priced on each.
| Model | Input /1M | Output /1M | Context | RAG answer |
|---|---|---|---|---|
| GLM-4.7 Zhipu | $0.600 | $2.20 | 200K | $0.0061 |
| GLM-5 Zhipu | $1.00 | $3.20 | 200K | $0.0099 |
| Gemini 3.5 Flash-Lite Google | $0.300 | $2.50 | 1.0M | $0.0039 |
| Mistral Large 4 Mistral | $0.700 | $2.10 | 1.0M | $0.0069 |
Alternatives to GLM-4.7
Pricing Details
ZhipuWorkhorse mid-tier GLM. Cached input $0.11/1M. Available via Z.ai direct, AWS Bedrock, Vertex AI Model Garden, Cerebras, Together, OpenRouter.
Input / 1M tokens
$0.6
Output / 1M tokens
$2.2
Context Window
200K
Max Output
128K
Price History
No price change recorded since 2026-08-03, when this site started tracking this model.
Frequently Asked Questions
Common questions about GLM-4.7 pricing and usage
How much does GLM-4.7 cost?
GLM-4.7 costs $0.6 per 1 million input tokens and $2.2 per 1 million output tokens. This pricing is set by Zhipu.
What tokenizer does GLM-4.7 use?
GLM-4.7 uses the cl100k_base tokenizer. This tokenizer has a vocabulary of ~100,000 tokens and is widely used across many models.
What is GLM-4.7's context window?
GLM-4.7 supports a context window of 200K tokens (200,000 tokens). The maximum output length is 128K tokens.
How does GLM-4.7 compare to other models?
On an 8,000-token-in, 600-token-out RAG answer, GLM-4.7 costs $0.0061 per request. The nearest-priced alternatives cost: GLM-5 (Zhipu) $0.0099, Gemini 3.5 Flash-Lite (Google) $0.0039, Mistral Large 4 (Mistral) $0.0069. The table above lists their full rates and context windows.
How do I count tokens for GLM-4.7?
Use the token counter at the top of this page or visit the homepage calculator. Paste your text and it will show the exact token count and cost for GLM-4.7 using the cl100k_base tokenizer.